# Relace models

[Get API key](https://vercel.com/d?to=%2F%5Bteam%5D%2F~%2Fai-gateway%3FshowCreateKeyModal%26utm_source%3Dgateway-providers-page%26utm_campaign%3Dai-gateway-providers&title=Get%20API%20key) [Read the docs](https://vercel.com/docs/ai-gateway)

Relace is a hosted inference provider for open-weight AI models, delivering cost-efficient access optimized for coding, reasoning, and agentic workloads.

| Model | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Regional Inference | Free Tier | Released |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |

| ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-flash-0731](/ai-gateway/models/deepseek-v4-flash-0731) | 1M | 0.4s | 139tps | $0.05/M | $0.10/M | Read:$0.01/M Write:— | — |  |  |  |  |  | 07/31/2026 |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |